BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
Abstract
Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a lower bound from chain, machine-capacity, and fleet-capacity relaxations. The bound equals the makespan at termination, so its per-step changes form a reward that sums to a constant minus the makespan. Because it never exceeds the attainable makespan, each candidate's bound increase is a proven rise of the makespan floor, which the policy reads as a price. The root bound certifies a completed schedule's suboptimality gap without a solver. On industry-motivated 10-module prefabricated-construction instances, explicit transport coupling outperforms a transport-penalty policy in every tested cell where loaded moves occupy at least 66% of fleet time and in none at or below 56%. Across five zero-shot 50- and 80-module production batches, BOLT outperforms the best dispatching-rule pair on four and the penalty policy on the three with long moves. In the three-vehicle 80-module batch, its mean makespan is 13.0% below the best pair and 4.2% below an hour-budget constraint-programming solver whose proven gap averages 34%. BOLT decides in 2.3-5.9 ms per event on one processor core and re-plans a disruption in seconds.
Related
- SLAB: Time-Lag-Aware Deep Reinforcement Learning for Flexible Job-Shop Scheduling in PPVC Module Factories
- Optimization method for flexible scheduling of digital twin industrial loads based on load side potential elasticity
- Automated Priority Rule Design for the Resource-Constrained Project Scheduling Problem: A Large Language Model-Guided Population-Based Search
- Joint Flexible Beamforming, Resource Allocation, and Task Buffering for Movable-Antenna Enabled MEC Systems
- Combining optimal low emission zones scheduling and electric vehicle purchase incentives for transport policy backcasting
BibTeX
@misc{zhang2026bolt,
title = {{BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport}},
author = {Ziheng Zhang and Wei Zhang and Yunyi Zhao and Zuming Liu and Wei Zhou and Boon Ping Gan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.22433},
eprint = {2610.22433},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.22433},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport
AU - Ziheng Zhang
AU - Wei Zhang
AU - Yunyi Zhao
AU - Zuming Liu
AU - Wei Zhou
AU - Boon Ping Gan
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.22433
UR - https://arxiv.org/abs/2610.22433
AB - Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a lower bound from chain, machine-capacity, and fleet-capacity relaxations. The bound equals the makespan at termination, so its per-step changes form a reward that sums to a constant minus the makespan. Because it never exceeds the attainable makespan, each candidate's bound increase is a proven rise of the makespan floor, which the policy reads as a price. The root bound certifies a completed schedule's suboptimality gap without a solver. On industry-motivated 10-module prefabricated-construction instances, explicit transport coupling outperforms a transport-penalty policy in every tested cell where loaded moves occupy at least 66% of fleet time and in none at or below 56%. Across five zero-shot 50- and 80-module production batches, BOLT outperforms the best dispatching-rule pair on four and the penalty policy on the three with long moves. In the three-vehicle 80-module batch, its mean makespan is 13.0% below the best pair and 4.2% below an hour-budget constraint-programming solver whose proven gap averages 34%. BOLT decides in 2.3-5.9 ms per event on one processor core and re-plans a disruption in seconds.
ER -